Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iese
    -0.07
     Photon
    -0.07
    /bit
    -0.07
    ric
    -0.07
     vlá
    -0.06
     compte
    -0.06
     hỗn
    -0.06
    odega
    -0.06
     dumping
    -0.06
    ปกครอง
    -0.06
    POSITIVE LOGITS
    controllers
    0.06
    （
    0.06
    unkt
    0.06
    [(
    0.06
     GPS
    0.06
     applied
    0.06
    ادل
    0.06
     відом
    0.06
    fps
    0.06
     riff
    0.06
    Act Density 0.038%

    No Known Activations